Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation
In this article, we tackle the issue of the limited quantity of manually sense annotated corpora for the task of word sense disambiguation, by exploiting the semantic relationships between senses such as synonymy, hypernymy and hyponymy, in order to compress the sense vocabulary of Princeton WordNet, and thus reduce the number of different sense tags that must be observed to disambiguate all words of the lexical database. We propose two different methods that greatly reduces the size of neural WSD models, with the benefit of improving their coverage without additional training data, and without impacting their precision. In addition to our method, we present a WSD system which relies on pre-trained BERT word vectors in order to achieve results that significantly outperform the state of the art on all WSD evaluation tasks.
PDF Abstract GWC 2019 PDF GWC 2019 Abstract
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Word Sense Disambiguation | SemEval 2007 Task 17 | SemCor+WNGC, hypernyms | F1 | 73.4 | # 1 | |
| Word Sense Disambiguation | SemEval 2007 Task 7 | SemCor+WNGC, hypernyms | F1 | 90.4 | # 1 | |
| Word Sense Disambiguation | SemEval 2013 Task 12 | SemCor+WNGC, hypernyms | F1 | 78.7 | # 1 | |
| Word Sense Disambiguation | SemEval 2015 Task 13 | SemCor+WNGC, hypernyms | F1 | 82.6 | # 1 | |
| Word Sense Disambiguation | SensEval 2 | SemCor+WNGC, hypernyms | F1 | 79.7 | # 1 | |
| Word Sense Disambiguation | SensEval 3 Task 1 | SemCor+WNGC, hypernyms | F1 | 77.8 | # 1 | |
| Word Sense Disambiguation | Supervised: | SemCor+WNGC, hypernyms | Senseval 2 | 79.7 | # 7 | |
| Senseval 3 | 77.8 | # 7 | ||||
| SemEval 2007 | 73.4 | # 8 | ||||
| SemEval 2013 | 78.7 | # 10 | ||||
| SemEval 2015 | 82.6 | # 7 |
